Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Jun 16, 2020
Date Accepted: Mar 21, 2021
Date Submitted to PubMed: Mar 25, 2021
Application of Artificial Intelligence for Screening COVID-19 Patients Using Digital Images: A Meta-Analysis
ABSTRACT
Background:
The Coronavirus Disease 2019 (COVID-2019) outbreak has spread rapidly and hospitals are overwhelmed with COVID-19 patients. While using swabs from patients is the main way for detecting coronavirus, analyzing chest images could offer an alternative to hospitals where healthcare personnel and testing kits are scarce. Deep learning, in particular, has shown impressive performances for analyzing medical images including COVID-19 pneumonia.
Objective:
To perform a systematic review with a meta-analysis of relevant studies to quantify the performance of the DL algorithms for automatic stratification of COVID-19 using chest images.
Methods:
A search strategy for use of PubMed, Scopus, Google Scholar, and Web of Science was developed (between January 1, 2020, and April 25) using the key terms COVID-19, coronavirus, SARS-CoV-2, novel corona, 2019-ncov and deep learning. Two authors independently extracted data on study characteristics, methods, risk of bias, and outcomes. Any disagreement between them was resolved by consensus.
Results:
Sixteen studies were included in the meta-analysis, including 5,896 chest images of COVID-19. The pooled sensitivity and specificity of DL for detecting COVID-19 was 0.95 (95%CI: 0.94-0.95), and 0.96 (95%CI: 0.96-0.97), respectively, with an SROC of 0.98. The positive likelihood, negative likelihood, and diagnostic odds ratio were 19.02 (12.83-28.19), 0.06(95%CI:0.04-0.10), and 368.07 (95%CI: 162.30-834.75), respectively. The pooled sensitivity and specificity for detecting Pneumonia was 0.93 (95%CI:0.92-0.94), and 0.95(95%CI: 0.94-0.95). The performance of radiologists for detecting COVID-19 was lower than DL; however, the performance of junior radiologists was improved when they used DL-based prediction tools.
Conclusions:
Our study findings show that deep learning models have immense potential accurately stratified COVID-19, and correctly differentiate from other pneumonia and normal patients. Implementation of deep learning-based tools can assist radiologists to correctly and quickly detect COVID-19 and to combat the COVID-19 pandemic. Clinical Trial: N/a
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.